mirror of
https://github.com/opencv/opencv.git
synced 2026-07-21 19:33:03 +04:00
Madan mohan Manokar
579a505734
core: SIMD optimizations for norm, distance and Hamming APIs. (Improves ORB & BRISK) #29335 Generic universal-intrinsic kernels (benefit all SIMD backends: NEON, AVX2, AVX-512, etc.), plus enabling wider dispatch for the norm module. - hal::normHamming: cached-pointer dispatch (resolve once, no per-call dispatch chain or trace region) + vector popcount path. cv::norm(NORM_HAMMING) and binary-descriptor matching (BFMatcher ORB/BRISK/FREAK via cv::batchDistance). - hal::normL2Sqr_ / normL1_: direct inlinable kernels with single-vector tail (cv::batchDistance / BFMatcher float L2/L1, cv::kmeans). - cv::norm masked NORM_INF: deinterleave SIMD for multichannel + back-step tail. - cv::norm(src1, src2, type, mask): SIMD masked norm-diff; INF is one templated kernel for all element types, plus uchar L1/L2 and int L1 kernels. - Enable AVX512_SKX/AVX512_ICL dispatch for the norm module. - features2d: add BFMatcher knnMatch perf tests (float L2/L1, binary Hamming). - ORB and BRISK performance improved ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
92 lines
2.8 KiB
C++
92 lines
2.8 KiB
C++
// This file is part of OpenCV project.
|
|
// It is subject to the license terms in the LICENSE file found in the top-level directory
|
|
// of this distribution and at http://opencv.org/license.html.
|
|
//
|
|
// Copyright (C) 2026, Advanced Micro Devices, Inc., all rights reserved.
|
|
|
|
// Brute-force descriptor matching perf tests. These exercise the core distance
|
|
// kernels (hal::normL2Sqr_ / normL1_ / normHamming via cv::batchDistance) that
|
|
// back BFMatcher, which is how float descriptors (SIFT 128-d, SURF 64-d) and
|
|
// binary descriptors (ORB 32-byte) are matched.
|
|
|
|
#include "perf_precomp.hpp"
|
|
|
|
namespace opencv_test
|
|
{
|
|
using namespace perf;
|
|
|
|
// (descriptor dimension, query/train descriptor count)
|
|
typedef tuple<int, int> Dim_Count_t;
|
|
typedef TestBaseWithParam<Dim_Count_t> DescriptorMatcherFixture;
|
|
|
|
// Float descriptors matched with L2 (SIFT=128, SURF=64) — uses hal::normL2Sqr_.
|
|
PERF_TEST_P(DescriptorMatcherFixture, bfmatch_knn_L2_float,
|
|
testing::Combine(
|
|
testing::Values(64, 128), // SURF, SIFT descriptor sizes
|
|
testing::Values(512, 1000)
|
|
))
|
|
{
|
|
const int dim = get<0>(GetParam());
|
|
const int count = get<1>(GetParam());
|
|
|
|
Mat query(count, dim, CV_32F);
|
|
Mat train(count, dim, CV_32F);
|
|
declare.in(query, train, WARMUP_RNG);
|
|
declare.time(60);
|
|
|
|
BFMatcher matcher(NORM_L2, false);
|
|
std::vector<std::vector<DMatch> > matches;
|
|
|
|
TEST_CYCLE() matcher.knnMatch(query, train, matches, 2);
|
|
|
|
SANITY_CHECK_NOTHING();
|
|
}
|
|
|
|
// Float descriptors matched with L1 — uses hal::normL1_.
|
|
PERF_TEST_P(DescriptorMatcherFixture, bfmatch_knn_L1_float,
|
|
testing::Combine(
|
|
testing::Values(64, 128),
|
|
testing::Values(512, 1000)
|
|
))
|
|
{
|
|
const int dim = get<0>(GetParam());
|
|
const int count = get<1>(GetParam());
|
|
|
|
Mat query(count, dim, CV_32F);
|
|
Mat train(count, dim, CV_32F);
|
|
declare.in(query, train, WARMUP_RNG);
|
|
declare.time(60);
|
|
|
|
BFMatcher matcher(NORM_L1, false);
|
|
std::vector<std::vector<DMatch> > matches;
|
|
|
|
TEST_CYCLE() matcher.knnMatch(query, train, matches, 2);
|
|
|
|
SANITY_CHECK_NOTHING();
|
|
}
|
|
|
|
// Binary descriptors matched with Hamming (ORB/BRISK=32 bytes) — uses hal::normHamming.
|
|
PERF_TEST_P(DescriptorMatcherFixture, bfmatch_knn_Hamming_binary,
|
|
testing::Combine(
|
|
testing::Values(32, 64), // ORB (32), BRISK/FREAK (64) byte sizes
|
|
testing::Values(512, 1000)
|
|
))
|
|
{
|
|
const int bytes = get<0>(GetParam());
|
|
const int count = get<1>(GetParam());
|
|
|
|
Mat query(count, bytes, CV_8U);
|
|
Mat train(count, bytes, CV_8U);
|
|
declare.in(query, train, WARMUP_RNG);
|
|
declare.time(60);
|
|
|
|
BFMatcher matcher(NORM_HAMMING, false);
|
|
std::vector<std::vector<DMatch> > matches;
|
|
|
|
TEST_CYCLE() matcher.knnMatch(query, train, matches, 2);
|
|
|
|
SANITY_CHECK_NOTHING();
|
|
}
|
|
|
|
} // namespace
|